© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 76043
    Prev
    Next
    INDEX
    Explanations

    interactive phrases that invite responses or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .tpl
    -0.07
    лÑĥги
    -0.07
    волÑı
    -0.07
     Dün
    -0.06
    baugh
    -0.06
     Schwartz
    -0.06
     Hansen
    -0.06
     Tun
    -0.06
    -NLS
    -0.06
     ãĢī
    -0.06
    POSITIVE LOGITS
     thoughts
    0.09
     think
    0.07
     thou
    0.07
    ega
    0.06
    thought
    0.06
    123
    0.06
    ilib
    0.06
     your
    0.06
    idar
    0.06
     thought
    0.06
    Activations Density 0.007%

    No Known Activations